What is vox-mcp CLAUDE.md?

A set of instructions for developing Vox MCP, an MCP server that provides access to multiple AI models. MCP is a standard way for AI tools to connect to external services.

Use it when running tests, adding or changing chat and model-listing features, exporting conversation threads, or maintaining the server.

It explains the project’s design rules, commands, file layout, and available tools so changes preserve its pass-through behavior and conversation memory.

How linxule/vox-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to linxule/vox-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/linxule/vox-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/linxule/vox-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/linxule/vox-mcp/claude-md.svg)](https://agentmods.dev/instructions/linxule/vox-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/linxule/vox-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/linxule/vox-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,383 This file is loaded in full into every session.

When invoked 2,383 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.02383	$0.02383
Opus 5	$0.01192	$0.01192
Sonnet 5	$0.00477	$0.00477
Haiku 4.5	$0.00238	$0.00238

Measured 6d ago against content hash a1665d4e63fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

vox-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vox MCP Development Guide

Design Principles

Pure API passthrough — prompts go to providers unmodified, responses come back unmodified
No system prompt injection — system_prompt is always None at the provider boundary
No response modification — no formatting, no coaching, no behavioral directives
No fabricated sampling params — temperature is omitted unless the caller sets one, so the model uses its own server-side default
Conversation memory is the sole value-add — in-memory threads via continuation_id

Quick Commands

uv sync                          # Install dependencies
uv run python server.py          # Run server (stdio MCP)
uv run python -c "import server" # Smoke test
uv run pytest                    # Run tests

Tool Surface

Tool	File	Purpose
`chat`	`tools/chat.py`	Multi-model AI gateway with file/image context
`listmodels`	`tools/listmodels.py`	Show available models and capabilities
`dump_threads`	`tools/dump_threads.py`	Export threads as JSON or Markdown

File Structure

server.py — MCP server, tool registration, request handling
config.py — shared constants (temperatures, limits, env defaults)
providers/ — model provider implementations (gemini, openai, anthropic, deepseek, moonshot, xai, openrouter, custom)
providers/registry.py — provider resolution and model routing
providers/shared/temperature.py — TemperatureConstraint ABC (Fixed, Range, Discrete)
providers/shared/thinking.py — ThinkingConstraint ABC (TokenBudget, EffortLevel, AlwaysOn)
providers/shared/model_capabilities.py — ModelCapabilities dataclass with constraint fields
conf/ — provider model capability JSON files
tools/chat.py — chat tool and ChatRequest model
tools/shared/base_tool.py — BaseTool with model resolution, token budgeting, file handling
tools/shared/base_models.py — ToolRequest base model, shared field descriptions
tools/simple/base.py — SimpleTool (request -> model -> response pattern)
utils/conversation_memory.py — thread creation, turn management, file tracking
utils/storage_backend.py — in-memory storage with TTL
utils/thread_persistence.py — append-only JSONL shadow persistence, cold-reload from disk
utils/markdown_export.py — markdown rendering with YAML frontmatter
utils/model_context.py — token budget calculation per model
tests/ — unit tests

Read the full file on GitHub · 179 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

6d ago First seen · 179 lines · 2,383 tokens per session scan A a1665d4e63fe

Subscribe to this mod's changes

vox-mcp CLAUDE.md is an instructions file published in the GitHub repository linxule/vox-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,383 tokens to every session, about $0.0119 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

LLM ai anthropic deepseek gemini mcp

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vox-mcp: Instructions file for Claude Code